Converts the quantized `input` tensor into a lower-precision `output`.
Converts the quantized `input` tensor into a lower-precision `output`, using the output range specified with `requested_output_min` and `requested_output_max`.
`[input_min, input_max]` are scalar floats that specify the range for the float interpretation of the `input` data. For example, if `input_min` is -1.0f and `input_max` is 1.0f, and we are dealing with `quint16` quantized data, then a 0 value in the 16-bit data should be interpreted as -1.0f, and a 65535 means 1.0f.
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
static <U extends TType> Requantize<U> | |
Output<U> |
output()
|
Output<TFloat32> |
outputMax()
The requested_output_max value is copied into this output.
|
Output<TFloat32> |
outputMin()
The requested_output_min value is copied into this output.
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public static Requantize<U> create (Scope scope, Operand<? extends TType> input, Operand<TFloat32> inputMin, Operand<TFloat32> inputMax, Operand<TFloat32> requestedOutputMin, Operand<TFloat32> requestedOutputMax, Class<U> outType)
Factory method to create a class wrapping a new Requantize operation.
Parameters
scope | current scope |
---|---|
inputMin | The float value that the minimum quantized input value represents. |
inputMax | The float value that the maximum quantized input value represents. |
requestedOutputMin | The float value that the minimum quantized output value represents. |
requestedOutputMax | The float value that the maximum quantized output value represents. |
outType | The type of the output. Should be a lower bit depth than Tinput. |
Returns
- a new instance of Requantize